Control of Complex Systems Using Bayesian Networks and Genetic Algorithm

TL;DR

This paper introduces a novel control method for complex systems, specifically fermentation processes, using Bayesian neural networks trained with hybrid Monte Carlo and a genetic algorithm for feedback control, improving accuracy.

Contribution

It combines Bayesian neural networks with genetic algorithms for process control, providing a new approach to optimize complex system outputs with confidence levels.

Findings

Significant reduction in output-target distance

Effective control of fermentation process

Maintains confidence level in predictions

Abstract

A method based on Bayesian neural networks and genetic algorithm is proposed to control the fermentation process. The relationship between input and output variables is modelled using Bayesian neural network that is trained using hybrid Monte Carlo method. A feedback loop based on genetic algorithm is used to change input variables so that the output variables are as close to the desired target as possible without the loss of confidence level on the prediction that the neural network gives. The proposed procedure is found to reduce the distance between the desired target and measured outputs significantly.